Lee Hye Won, Kim Eunjin, Na Inye, Kim Chan Kyo, Seo Seong Il, Park Hyunjin
Samsung Medical Center, Department of Urology, Sungkyunkwan University School of Medicine, Seoul 06351, Republic of Korea.
Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon 16419, Republic of Korea.
Cancers (Basel). 2023 Jun 29;15(13):3416. doi: 10.3390/cancers15133416.
Radical prostatectomy (RP) is the main treatment of prostate cancer (PCa). Biochemical recurrence (BCR) following RP remains the first sign of aggressive disease; hence, better assessment of potential long-term post-RP BCR-free survival is crucial. Our study aimed to evaluate a combined clinical-deep learning (DL) model using multiparametric magnetic resonance imaging (mpMRI) for predicting long-term post-RP BCR-free survival in PCa. A total of 437 patients with PCa who underwent mpMRI followed by RP between 2008 and 2009 were enrolled; radiomics features were extracted from T2-weighted imaging, apparent diffusion coefficient maps, and contrast-enhanced sequences by manually delineating the index tumors. Deep features from the same set of imaging were extracted using a deep neural network based on pretrained EfficentNet-B0. Here, we present a clinical model (six clinical variables), radiomics model, DL model (DLM-Deep feature), combined clinical-radiomics model (CRM-Multi), and combined clinical-DL model (CDLM-Deep feature) that were built using Cox models regularized with the least absolute shrinkage and selection operator. We compared their prognostic performances using stratified fivefold cross-validation. In a median follow-up of 61 months, 110/437 patients experienced BCR. CDLM-Deep feature achieved the best performance (hazard ratio [HR] = 7.72), followed by DLM-Deep feature (HR = 4.37) or RM-Multi (HR = 2.67). CRM-Multi performed moderately. Our results confirm the superior performance of our mpMRI-derived DL algorithm over conventional radiomics.
根治性前列腺切除术（RP）是前列腺癌（PCa）的主要治疗方法。RP术后的生化复发（BCR）仍然是侵袭性疾病的首要迹象；因此，更好地评估RP术后潜在的长期无BCR生存率至关重要。我们的研究旨在评估一种结合临床深度学习（DL）模型，该模型使用多参数磁共振成像（mpMRI）来预测PCa患者RP术后的长期无BCR生存率。共有437例在2008年至2009年间接受了mpMRI检查并随后接受RP治疗的PCa患者入组；通过手动勾勒索引肿瘤，从T2加权成像、表观扩散系数图和对比增强序列中提取了影像组学特征。使用基于预训练的EfficentNet-B0的深度神经网络从同一组影像中提取深度特征。在此，我们展示了一个临床模型（六个临床变量）、影像组学模型、DL模型（DLM-深度特征）、联合临床-影像组学模型（CRM-多因素）和联合临床-DL模型（CDLM-深度特征），这些模型是使用采用最小绝对收缩和选择算子正则化的Cox模型构建的。我们使用分层五重交叉验证比较了它们的预后性能。在中位随访61个月时，437例患者中有110例经历了BCR。CDLM-深度特征表现最佳（风险比[HR]=7.72），其次是DLM-深度特征（HR=4.37）或RM-多因素（HR=2.67）。CRM-多因素表现中等。我们的结果证实了我们基于mpMRI的DL算法优于传统影像组学。
